api.postqueen.ai. MCP, the Model Context Protocol, is how AI agents use outside tools. Give your agent one address and it can list your channels, schedule posts, add media and read how your posts did. There is nothing to install or run on your side.

Pick an address
Clients that still use the older SSE transport can connect to
https://api.postqueen.ai/sse/YOUR_API_KEY.
- Key address
- Bearer header
- Sign-in address
The API key is part of the address, so there is nothing else to fill in. Most agents take this one.
Where the key is
Where the API key is: in the app, open Connections > API Keys. Only a workspace Admin or Super Admin can reveal or rotate it; other members see it masked. A workspace has one key, and each agent card on Connections shows your MCP address with the key already filled in.
Sign in instead of a key
1
Add the sign-in address
Paste
https://api.postqueen.ai/mcp-oauth-dynamic into the agent, with no slash at the end. Leave any client ID and secret fields empty: the agent registers itself with PostQueen.2
Sign in and approve
The agent opens PostQueen in your browser. Sign in and approve the access. Only a workspace Admin or Super Admin can approve it.
3
Use it
The access does not expire on its own. To end it, open Connections > Approved Apps in PostQueen and revoke it.
What the agent can do
The tools come in seven groups. The agent picks the ones it needs from what you ask.
Every tool, with what it takes and what it returns: MCP tools.
What it cannot do yet
- Delete a post.
- Change a post’s text or time, or move a draft to scheduled. It can change a post’s settings.
- Read channel numbers such as follower counts.
Check that it works
Ask your agent:integrationList and answers with the channels you connected. Channels that are turned off or need to be reconnected are left out. If the agent shows no PostQueen tools, or the connection fails, see troubleshooting agents.
Next steps
Every agent
Which agents can post to PostQueen, and how each one connects.
The MCP tools
What each of the 22 tools does, and what an agent cannot do.
Prompts and tool calls
The order an agent calls the tools in, with prompts that work.
Troubleshooting agents
What to do when a connection or a command fails.